Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/107483
Title: Human or Machine? It Is Not What You Write, But How You Write It
Authors: Leiva, Luis A.
Díaz Cabrera, Moisés 
Ferrer Ballester, Miguel Ángel 
Plamondon, Rejean
UNESCO Clasification: 2405 Biometría
Issue Date: 2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Project: Generacion de Un Marco Unificado Para El Desarrollo de Patrones Biometricos de Comportamiento 
Journal: Proceedings - International Conference on Pattern Recognition 
Conference: 25th International Conference on Pattern Recognition (ICPR 2020) 
Abstract: Online fraud often involves identity theft. Since most security measures are weak or can be spoofed, we investigate a more nuanced and less explored avenue: behavioral biometrics via handwriting movements. This kind of data can be used to verify whether a user is operating a device or a computer application, so it is important to distinguish between human and machine-generated movements reliably. For this purpose, we study handwritten symbols (isolated characters, digits, gestures, and signatures) produced by humans and machines, and compare and contrast several deep learning models. We find that if symbols are presented as static images, they can fool state-of-the-art classifiers (near 75% accuracy in the best case) but can be distinguished with remarkable accuracy if they are presented as temporal sequences (95% accuracy in the average case). We conclude that an accurate detection of fake movements has more to do with how users write, rather than what they write. Our work has implications for computerized systems that need to authenticate or verify legitimate human users, and provides an additional layer of security to keep attackers at bay.
URI: http://hdl.handle.net/10553/107483
ISBN: 978-1-7281-8808-9
ISSN: 1051-4651
DOI: 10.1109/ICPR48806.2021.9411949
Source: Proceedings - International Conference on Pattern Recognition [ISSN 1051-4651], p. 2612-2619, (Mayo 2021)
Appears in Collections:Actas de congresos
Show full item record

Page view(s)

74
checked on Jun 21, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.